© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14776
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and daily activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     آذ
    -0.06
     возÑĢаÑģÑĤ
    -0.06
    alah
    -0.06
    Lifetime
    -0.06
    rio
    -0.06
    çĶ²
    -0.06
    folios
    -0.06
     tonight
    -0.06
    sz
    -0.06
    ãĤ«ãĥ¼
    -0.06
    POSITIVE LOGITS
     Reduced
    0.07
     productivity
    0.07
     work
    0.07
     reduction
    0.07
    ongs
    0.07
     employee
    0.07
     reductions
    0.07
    Reduc
    0.07
    anness
    0.06
     employees
    0.06
    Activations Density 0.001%

    No Known Activations